INDEX
Explanations
mentions of presidential elections and related political terminology
New Auto-Interp
Negative Logits
fak
-0.20
zza
-0.16
aiser
-0.16
echn
-0.16
fare
-0.16
ÃĸL
-0.14
/we
-0.14
amina
-0.14
chin
-0.14
iferay
-0.14
POSITIVE LOGITS
-level
0.17
-Level
0.17
iership
0.15
ism
0.15
ist
0.15
id
0.15
owned
0.14
contender
0.14
TY
0.14
hopeful
0.14
Activations Density 0.019%